Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    plus/minus symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    丝毫
    -0.06
     Morg
    -0.06
     Ced
    -0.06
    据此
    -0.06
    /XMLSchema
    -0.06
    𬭎
    -0.06
    ござ
    -0.06
     öz
    -0.06
    辗转
    -0.06
    _AG
    -0.06
    POSITIVE LOGITS
     heater
    0.09
    نتهاء
    0.07
     valve
    0.07
    erie
    0.07
     PLAYER
    0.07
    emetery
    0.07
    Servers
    0.07
    Ứ
    0.07
    要闻
    0.07
     với
    0.07
    Act Density 0.025%

    No Known Activations